其他
ViT:视觉Transformer backbone网络ViT论文与代码详解
Visual Transformer
Author:louwill
Machine Learning Lab
ILSVRC-2012 ImageNet dataset:1000 classes ImageNet-21k:21k classes JFT:18k High Resolution Images
CIFAR-10/100 Oxford-IIIT Pets Oxford Flowers-102 VTAB
pip install vit-pytorch
import torch
from vit_pytorch import ViT
# 创建ViT模型实例
v = ViT(
image_size = 256,
patch_size = 32,
num_classes = 1000,
dim = 1024,
depth = 6,
heads = 16,
mlp_dim = 2048,
dropout = 0.1,
emb_dropout = 0.1
)
# 随机化一个图像输入
img = torch.randn(1, 3, 256, 256)
# 获取输出
preds = v(img) # (1, 1000)
image_size:原始图像尺寸
patch_size:图像块的尺寸
num_classes:类别数量
dim:Transformer隐变量维度大小
depth:Transformer编码器层数
Heads:MSA中的head数
dropout:失活比例
emb_dropout:嵌入层失活比例
# 导入相关模块
import torch
from torch import nn, einsum
import torch.nn.functional as F
from einops import rearrange, repeat
from einops.layers.torch import Rearrange
# 辅助函数,生成元组
def pair(t):
return t if isinstance(t, tuple) else (t, t)
# 规范化层的类封装
class PreNorm(nn.Module):
def __init__(self, dim, fn):
super().__init__()
self.norm = nn.LayerNorm(dim)
self.fn = fn
def forward(self, x, **kwargs):
return self.fn(self.norm(x), **kwargs)
# FFN
class FeedForward(nn.Module):
def __init__(self, dim, hidden_dim, dropout = 0.):
super().__init__()
self.net = nn.Sequential(
nn.Linear(dim, hidden_dim),
nn.GELU(),
nn.Dropout(dropout),
nn.Linear(hidden_dim, dim),
nn.Dropout(dropout)
)
def forward(self, x):
return self.net(x)
# Attention
class Attention(nn.Module):
def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
super().__init__()
inner_dim = dim_head * heads
project_out = not (heads == 1 and dim_head == dim)
self.heads = heads
self.scale = dim_head ** -0.5
self.attend = nn.Softmax(dim = -1)
self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)
self.to_out = nn.Sequential(
nn.Linear(inner_dim, dim),
nn.Dropout(dropout)
) if project_out else nn.Identity()
def forward(self, x):
b, n, _, h = *x.shape, self.heads
qkv = self.to_qkv(x).chunk(3, dim = -1)
q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), qkv)
dots = einsum('b h i d, b h j d -> b h i j', q, k) * self.scale
attn = self.attend(dots)
out = einsum('b h i j, b h j d -> b h i d', attn, v)
out = rearrange(out, 'b h n d -> b n (h d)')
return self.to_out(out)
# 基于PreNorm、Attention和FFN搭建Transformer
class Transformer(nn.Module):
def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
super().__init__()
self.layers = nn.ModuleList([])
for _ in range(depth):
self.layers.append(nn.ModuleList([
PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
]))
def forward(self, x):
for attn, ff in self.layers:
x = attn(x) + x
x = ff(x) + x
return x
(3) 搭建ViT
class ViT(nn.Module):
def __init__(self, *, image_size, patch_size, num_classes, dim, depth, heads, mlp_dim, pool = 'cls', channels = 3, dim_head = 64, dropout = 0., emb_dropout = 0.):
super().__init__()
image_height, image_width = pair(image_size)
patch_height, patch_width = pair(patch_size)
assert image_height % patch_height == 0 and image_width % patch_width == 0, 'Image dimensions must be divisible by the patch size.'
# patch数量
num_patches = (image_height // patch_height) * (image_width // patch_width)
# patch维度
patch_dim = channels * patch_height * patch_width
assert pool in {'cls', 'mean'}, 'pool type must be either cls (cls token) or mean (mean pooling)'
# 定义块嵌入
self.to_patch_embedding = nn.Sequential(
Rearrange('b c (h p1) (w p2) -> b (h w) (p1 p2 c)', p1 = patch_height, p2 = patch_width),
nn.Linear(patch_dim, dim),
)
# 定义位置编码
self.pos_embedding = nn.Parameter(torch.randn(1, num_patches + 1, dim))
# 定义类别向量
self.cls_token = nn.Parameter(torch.randn(1, 1, dim))
self.dropout = nn.Dropout(emb_dropout)
self.transformer = Transformer(dim, depth, heads, dim_head, mlp_dim, dropout)
self.pool = pool
self.to_latent = nn.Identity()
# 定义MLP
self.mlp_head = nn.Sequential(
nn.LayerNorm(dim),
nn.Linear(dim, num_classes)
)
# ViT前向流程
def forward(self, img):
# 块嵌入
x = self.to_patch_embedding(img)
b, n, _ = x.shape
# 追加类别向量
cls_tokens = repeat(self.cls_token, '() n d -> b n d', b = b)
x = torch.cat((cls_tokens, x), dim=1)
# 追加位置编码
x += self.pos_embedding[:, :(n + 1)]
# dropout
x = self.dropout(x)
# 输入到transformer
x = self.transformer(x)
x = x.mean(dim = 1) if self.pool == 'mean' else x[:, 0]
x = self.to_latent(x)
# MLP
return self.mlp_head(x)
小结
参考资料:
An Image Is Worth 16X16 Words: Transformers for Image Recognition at Scale
https://github.com/lucidrains/vit-pytorch
https://mp.weixin.qq.com/s/ozUHHGMqIC0-FRWoNGhVYQ
往期精彩: